Leaf species and disease classification using multiscale parallel deep CNN architecture

Russel, Newlin Shebiah; Arivazhagan, S.

doi:10.1007/s00521-022-07521-w

Cited by 45 publications

(7 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Comparative analysis results of the study with similar studies in the literature in the study conducted by Russel and Selvaraj [24], the study is 9.63% more successful. Moreover, it was observed that the highest classification success rate was obtained among the classification studies conducted with ten categories (Figure 10).…”

Section: Figure 10supporting

confidence: 66%

Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods

Kayaalp

2024

ITC

View full text Add to dashboard Cite

Leaf images are often used to detect plant diseases because most disease symptoms appear on the leaves. Analyzes performed by experts in the laboratory environment are expensive and time consuming. Therefore, there is a need for automated plant disease detection systems that are both economical and can help diagnose early symptoms more accurately. In this study, a deep learning-based methodology is presented for the classification of leaf diseases of plants, which are very similar in color, texture, vein and shape and cannot be noticed by non-experts, which are important for traditional medicine and pharmaceutical industry. In the model development process, 7 pre-learning deep learning algorithms and an image data set created from plant leaves in 10 categories were preferred. The proposed model classifies the plant type and diseased condition in the dataset. In the first step of training the model, different learning rates were tested with optimum hyperparameters. In the second part, a test accuracy rate of 98.69% was achieved with the DenseNet121 model, with increased data. At the last stage, after the edge detection processes, the test accuracy value of 67.92% was reached with the DenseNet 121 model.

show abstract

Section: Figure 10supporting

confidence: 66%

Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods

Kayaalp

2024

ITC

View full text Add to dashboard Cite

show abstract

“…Images of different leaves, diseases, and degrees of infection were expected to be identified. Famous public datasets, such as Plant Village ( https://arxiv.org/abs/1511.08060 ), and some of its improved versions gained attention of many researchers, which led to the emergence of new ideas for disease classification [ 9 ]. With the demand for precision plant disease management, advanced tasks like localization of the disease symptom, disease spots distribution analysis, and other phenotypic feature extraction need more attention.…”

Section: Introductionmentioning

confidence: 99%

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

et al. 2023

View full text Add to dashboard Cite

Deep learning and computer vision have become emerging tools for diseased plant phenotyping. Most previous studies focused on image-level disease classification. In this paper, pixel-level phenotypic feature (the distribution of spot) was analyzed by deep learning. Primarily, a diseased leaf dataset was collected and the corresponding pixel-level annotation was contributed. A dataset of apple leaves samples was used for training and optimization. Another set of grape and strawberry leaf samples was used as an extra testing dataset. Then, supervised convolutional neural networks were adopted for semantic segmentation. Moreover, the possibility of weakly supervised models for disease spot segmentation was also explored. Grad-CAM combined with ResNet-50 (ResNet-CAM), and that combined with a few-shot pretrained U-Net classifier for weakly supervised leaf spot segmentation (WSLSS), was designed. They were trained using image-level annotations (healthy versus diseased) to reduce the cost of annotation work. Results showed that the supervised DeepLab achieved the best performance (IoU = 0.829) on the apple leaf dataset. The weakly supervised WSLSS achieved an IoU of 0.434. When processing the extra testing dataset, WSLSS realized the best IoU of 0.511, which was even higher than fully supervised DeepLab (IoU = 0.458). Although there was a certain gap in IoU between the supervised models and weakly supervised ones, WSLSS showed stronger generalization ability than supervised models when processing the disease types not involved in the training procedure. Furthermore, the contributed dataset in this paper could help researchers get a quick start on designing their new segmentation methods in future studies.

show abstract

“…While deep learning has been extensively applied to crack detection in civil infrastructure, relatively fewer studies have focused specifically on historical buildings [24]. The unique architectural characteristics and preservation challenges associated with historical structures necessitate tailored approaches for crack detection and analysis [25].…”

Section: Deep Learning Techniques Such As Deep Convolutionalmentioning

confidence: 99%

A Deep Residual Network Designed for Detecting Cracks in Buildings of Historical Significance

Makhanova,

Beissenova,

Madiyarova

et al. 2024

ijacsa

View full text Add to dashboard Cite

This research paper investigates the application of deep learning techniques, specifically convolutional neural networks (CNNs), for crack detection in historical buildings. The study addresses the pressing need for non-invasive and efficient methods of assessing structural integrity in heritage conservation. Leveraging a dataset comprising images of historical building surfaces, the proposed CNN model demonstrates high accuracy and precision in identifying surface cracks. Through the integration of convolutional and fully connected layers, the model effectively distinguishes between positive and negative instances of cracks, facilitating automated detection processes. Visual representations of crack finding cases in ancient buildings validate the model's efficacy in real-world applications, offering tangible evidence of its capability to detect structural anomalies. While the study highlights the potential of deep learning algorithms in heritage preservation efforts, it also acknowledges challenges such as model generalization, computational complexity, and interpretability. Future research endeavors should focus on addressing these challenges and exploring new avenues for innovation to enhance the reliability and accessibility of crack detection technologies in cultural heritage conservation. Ultimately, this research contributes to the development of sustainable solutions for safeguarding architectural heritage, ensuring its preservation for future generations.

show abstract

Leaf species and disease classification using multiscale parallel deep CNN architecture

Cited by 45 publications

References 37 publications

Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods

Classification of Medicinal Plant Leaves for Types and Diseases with Hybrid Deep Learning Methods

Phenotypic Analysis of Diseased Plant Leaves Using Supervised and Weakly Supervised Deep Learning

A Deep Residual Network Designed for Detecting Cracks in Buildings of Historical Significance

Contact Info

Product

Resources

About